© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204695
    Prev
    Next
    INDEX
    Explanations

    market movements and sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     오래
    0.39
     represented
    0.39
    lj
    0.39
    具备
    0.39
    ﻹ
    0.38
     দায়িত্বে
    0.38
     justa
    0.38
     ca
    0.38
     kraja
    0.38
     ปก
    0.38
    POSITIVE LOGITS
     fears
    0.50
     Fears
    0.49
     feared
    0.48
     fearing
    0.47
     fearful
    0.41
     sợ
    0.39
    ))$.
    0.37
    ইং
    0.37
    இதனால்
    0.37
    कला
    0.37
    Activations Density 0.001%

    No Known Activations